Infrastructure · Infrastructure resource
Edge Device
Infrastructure resourceInfrastructureInfrastructureVariation point (abstract)arc:EdgeDevice
An abstract resource-constrained compute device at or near the point of data generation that runs inference locally, possibly without network connectivity.
Responsibility. Hosts on-device inference close to the data source.
Also known as: Edge node, Embedded device, Embedded robot/automotive processor
Variants
| Variant | When to choose |
|---|---|
| Edge FPGA Device | Choose for specialised applications needing ultra-low latency when hardware programming expertise is available. |
| Edge GPU Device | Choose for robotics and autonomous systems needing programmable acceleration across many model types, accepting higher power draw. |
| Edge NPU Device | Choose for mobile and embedded products where dedicated AI acceleration must consume minimal power. |
| Edge TPU Device | Choose for battery-powered devices running standard neural network architectures. |
| Microcontroller Device | Choose for sensor-scale, battery-powered deployments where memory and power budgets are minimal. |
Relationships
hosts structural
is audited by assurance
Design guidance
- MUST protect models and data with on-device encryption, secure boot and hardware-backed attestation because physical access enables attacks.
Quantitative guidance
As stated by the sources; verify before use.
- Edge inference < 10 ms vs 200-500 ms cloud round trip (Ch4.3).
- Embedded automotive systems with 64 MB total RAM cannot dedicate ~20% to a single pathfinding query (Ch5.6).
Classification
- Patterns
- Secure bootOn-device encryptionOffline operation
- Technologies
- NVIDIA JetsonGoogle Coral Edge TPUApple Neural EngineQualcomm SnapdragonIntel Movidius
- Quality attributes
- Performance efficiency (ISO/IEC 25010)Privacy (NIST AI RMF: privacy-enhanced)Transparency and accountability (NIST AI RMF: accountable and transparent)
- Risks mitigated
- Network round-trip latencyDependence on connectivitySensitive data leaving the device
Sources
- Ch4.3: T. Nguyen, "Container Orchestration and Edge Deployment," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 4.3. ISBN: 9798244538229.
- Ch5.6: T. Nguyen, "A* Search and Replaning," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 5.6. ISBN: 9798244538229.